Báo cáo khoa học: "Learning Constraint Grammar-style disambiguation rules using Inductive Logic Programming" potx

... sources used in our experiments. 3.1 Inductive Logic Programming Inductive Logic Programming (Muggleton, 1991) employs techniques from Machine Learning and Logic Programming to build first-order ... knowledge about disambiguation examples together with a powerful modeling tech- nique to induce theories based on the examples and background knowledge. This is achieved using...

Ngày tải lên: 08/03/2014, 02:21

... opti- mizer in its own metric. In Figure 2, single- objective PRO focusing on optimizing RIBES only achieves 0.68, but PMO-PRO using both BLEU and RIBES outperforms with 0.685. The third observation ... modifies MERT to optimize a single metric subject to the constraint that it does not degrade others. These approaches all require some setting of constraint strength or combination weight...

Ngày tải lên: 19/02/2014, 19:20

... Workshop. Yusuke Miyao. 2005. Probabilistic disambiguation mod- els for wide-coverage HPSG parsing. In ACL ’05. Radford M. Neal. 1993. Probabilistic inference using markov chain Monte Carlo methods. ... automatically define a probabilistic SCF inventory, we outperform systems with hand- crafted rules and inventories, using identical syntac- tic features. Second, by replacing the syntac...

Ngày tải lên: 19/02/2014, 19:20

... groups of more than two lan- guages. Using a group of languages for disambigua- tion will likely lead to increased and more accurate disambiguation, as more constraints are imposed on the data. Probably ... pro- cess. We present a system for simultaneous and ac- curate partial parse disambiguation of multiple lan- guages. Using the pre-selected set of parses returned by the system, the...

Ngày tải lên: 19/02/2014, 19:20

... training and test data. Since we are using Wikipedia bilingual titles as the gold standard, we exclude any snippets from the wikipedia.org domain, so that we are not using Wikipedia article content ... recognition), and then query a search engine for webpages in the target language (e.g., Chinese) using the advance search function. Subsequently, we retrieve mixed-code snippets and...

Ngày tải lên: 19/02/2014, 19:20

... inference and update rules for P and Q are omitted, but can be found in (Srebro and Jaakkola, 2003) 141 3 Experiment Setting Task: We choose the fine-grained All-Words Sense Disambiguation task, ... system on SE2 and SE3. 4 Experiment Results The disambiguation results (K = 100) are summa- rized in Table 2. We also present in Table 3 results using other values of dimensions K for wmfve...

Ngày tải lên: 19/02/2014, 19:20

... parameter τ is referred to as the tempera- ture, with a higher temperature causing more ex- ploration, and a lower temperature causing more exploitation. In our experiments τ = 2. Acting with this exploration ... semantics in our paper is simpler, eschewing quantitative as- pects and path descriptors, and instead focusing on reference objects and frames of reference. This simplifies the learni...

Ngày tải lên: 20/02/2014, 04:20

... Athens, Greece. Roberto Navigli. 2009b. Word Sense Disambiguation: A survey. ACM Computing Surveys, 41(2):1–69. Michael P. Oakes. 2005. Using hearst’s rules for the automatic acquisition of hyponyms ... words ag- gregated using synonymy, similarity, or subtrees of a thesaurus. However, salient word selection and aggregation is non-obvious and furthermore it falls into word sense disa...

Ngày tải lên: 20/02/2014, 04:20

... that the word vectors of our model should predict the sentiment label using some appropriate predictor, ˆs = f (φ w ). (8) Using an appropriate predictor function f(x) we map a word vector φ w to ... in a high-dimensional space. The general approach has proven useful in tasks such as word sense disambiguation, named entity recognition, part of speech tagging, and document retrieval (Turn...

Ngày tải lên: 20/02/2014, 04:20

... systems. Syntax- based MT often suffers from inadequate constraints in the translation rules extracted, or from striving to combine these rules together towards a full deriva- tion. Recent research ... different. We do not employ rules that are grounded to lexical context (‘gap’ rules) , relying in- stead on the reordering-aware non-terminal set and related unary and binary rules. The...

Ngày tải lên: 20/02/2014, 04:20